docs: tighten prose audit after master retarget

This commit is contained in:
Tianyi Cui
2026-07-13 16:24:32 +08:00
parent 17e04a1c70
commit c45d7927cf
192 changed files with 1047 additions and 4078 deletions

View File

@@ -34,67 +34,35 @@ declare module 'cordis' {
interface Events {
/**
* A session was created in the store. A synchronous listener throw vetoes
* publication and rollback emits the matching `session/disposed` edge;
* returned-promise rejection is observed and logged but cannot retroactively
* veto this synchronous boundary. A synchronous listener that requests the
* advanced detach does not remove the entry immediately: removal and the
* paired `session/disposed` edge wait until the creation dispatch unwinds.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is the
* session's owner scope, captured when the session was ENTERED (an agent's
* session is entered through `agent.ctx`, so its events dispatch in that
* agent's scope; a bare `sessions.create()` from a plain plugin dispatches
* subject-less). A listener registered through `agent.ctx` hears only that
* agent's sessions; a plain plugin listener hears every session.
* Emitted after session publication. A synchronous throw vetoes and rolls
* back with a paired disposal; detach requested during dispatch is deferred.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners
* receive only sessions entered through that agent's context.
* @param session - the session just entered and announced.
* @mode emit
*/
'session/created'(this: Scoped<Session>, session: Session): void
/**
* A previously announced session left the store. Emitted exactly once on
* normal detach or publication rollback, and never for a prepared/entered
* session whose `session/created` announcement did not begin. Listener
* failures (including returned-promise rejections) are logged and contained
* per listener so teardown always reaches quiescence.
* Scope-filtered dispatch uses the same owner carrier captured at entry;
* agent-scoped listeners hear only their own session's teardown.
* Emitted once when an announced session leaves the store, including
* publication rollback. Listener failures are contained.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`) reuses the owner scope.
* @param session - the session that is no longer live in the store.
* @mode emit
*/
'session/disposed'(this: Scoped<Session>, session: Session): void
/**
* An event was appended to a session log (sync, fire-and-forget). This is
* the per-append feed a UI or invariant plugin tails. The log push is the
* commit point; synchronous throws and returned-promise rejections from
* observers are logged and contained per listener, so they cannot make a
* committed append appear to fail or starve later listeners. The exact
* callback list and Cordis internal-dispatch checks resolve before the push;
* callbacks themselves run only after it.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is the
* session's owner scope, captured when the session was ENTERED (an agent's
* session is entered through `agent.ctx`, so its events dispatch in that
* agent's scope; a bare `sessions.create()` from a plain plugin dispatches
* subject-less). A listener registered through `agent.ctx` hears only that
* agent's sessions; a plain plugin listener hears every session.
* Post-commit append feed. Observer failures are logged and contained.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners
* receive only events from sessions entered through that agent's context.
* @param session - the session whose log grew.
* @param event - the appended event, exactly as recorded.
* @mode emit
*/
'session/event'(this: Scoped<Session>, session: Session, event: SessionEvent): void
/**
* Awaited durability checkpoint. The agent loop awaits
* `ctx.sessions.flush(session)` at every turn end; persistence
* plugins (JSONL, SQLite) drain their write-behind buffers here and on
* fiber dispose. Awaited (parallel), not a waterfall: every listener runs
* and the caller waits for all of them, but none can veto. Dispatch it
* through {@link SessionStore.flush} — the store owns the carrier — never
* via a raw `ctx.parallel`.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): the carrier is the
* session's owner scope, captured when the session was ENTERED (an agent's
* session is entered through `agent.ctx`, so its events dispatch in that
* agent's scope; a bare `sessions.create()` from a plain plugin dispatches
* subject-less). A listener registered through `agent.ctx` hears only that
* agent's sessions; a plain plugin listener hears every session.
* Awaited parallel durability checkpoint; dispatch through
* {@link SessionStore.flush}. Scope-filtered dispatch
* (`@deepseek-ai/dsh-scope`) reuses the session's owner scope.
* @param session - the session whose buffered events must reach durable storage.
* @mode parallel
*/
@@ -102,15 +70,7 @@ declare module 'cordis' {
}
}
/**
* Renders a `context/message` or `steering/message` event as a tagged
* synthetic user-role message (the system-reminder pattern: zero adapter
* burden, models distinguish it from real user prompts by the envelope).
*
* Live-adapter review has validated the tagged-envelope rendering against
* current DeepSeek behavior; provider-specific mismatches belong in that
* adapter, not in the canonical session vocabulary.
*/
/** Render injected context as a tagged synthetic user-role message. */
function renderTagged(tag: string, content: ContentBlock[], source: MessageSource): ContentBlock[] {
const open = `<${tag} source=${JSON.stringify(source.kind)}>`
const close = `</${tag}>`

View File

@@ -1,17 +1,4 @@
/**
* Lossless-JSON validation and snapshot materialization for session data.
*
* The session event log is the durable source of truth (the event-sourcing / session-persistence RFCs): every
* `event.data` must round-trip losslessly through JSON so any persistence
* backend can store and reload it byte-identically. This invariant belongs to
* the log itself — `Session.append` enforces it at the source, so a
* non-serializable event never enters `session.events` and the live log can
* never diverge from what a backend can persist. Other public boundaries use
* {@link snapshotJsonValue} when they must validate and detach in one pass;
* {@link isJsonValue} remains the non-copying structural predicate.
*
* @module @deepseek-ai/dsh-session/json
*/
/** Lossless-JSON validation and detached snapshots for durable session data. @module @deepseek-ai/dsh-session/json */
/**
* A value that round-trips losslessly through JSON: `null`, a boolean, a finite
@@ -25,19 +12,9 @@
export type JsonValue = null | boolean | number | string | JsonValue[] | { [key: string]: JsonValue }
/**
* Materialize one detached lossless-JSON snapshot in a SINGLE recursive pass.
* Each array slot or own enumerable string-keyed object value is read exactly
* once, validated, and copied immediately. This is intentionally not
* `isJsonValue(value)` followed by `structuredClone(value)`: a stateful getter
* could return plain JSON to the check and an exotic class instance to the
* clone, whose prototype `structuredClone` would erase before a later check.
*
* Accepts the same scalar/object vocabulary as {@link isJsonValue}: arrays use
* the ordinary `Array.prototype` (subclass instances are not plain JSON
* containers), while null-prototype objects are accepted and normalized to
* ordinary plain objects. Sparse arrays, cycles, negative zero, non-finite
* numbers, unsupported scalar types, and exotic object or array shells return
* `undefined`. A throwing getter is a caller failure and propagates unchanged.
* Validate and detach lossless JSON in one read per property. Accepts ordinary
* arrays, plain or null-prototype objects, and JSON scalars; rejects sparse,
* cyclic, exotic, negative-zero, and non-finite values. Getter throws propagate.
*
* @param value - the candidate value to validate and detach.
* @returns the detached snapshot, or `undefined` when the value is not
@@ -104,28 +81,12 @@ export function snapshotJsonValue<T>(value: T): T | undefined {
}
/**
* Whether `value` is losslessly JSON-serializable: only `null`, finite numbers
* other than negative zero, booleans, strings, plain arrays, and plain objects
* of such values. Rejects `BigInt`, function, symbol, `undefined`, `-0` (which
* JSON rewrites to `0`), non-finite numbers (`NaN`/`Infinity`, which JSON turns
* into `null`), and exotic objects (`Map`/`Set`/`Date`/class instances) —
* anything `JSON.stringify` would drop, throw on, or convert lossily. Sparse
* arrays are rejected too: a hole serializes to `null`, so `[1, , 3]` would not
* round-trip. Detects circular references (which would throw) and reports them
* as non-serializable rather than propagating the throw.
*
* Scope — this is a structural plain-data predicate, not an invocation of
* `JSON.stringify`: only an object's OWN ENUMERABLE STRING-keyed properties are
* inspected (`Object.values`). Symbol-keyed and non-enumerable properties are
* omitted from the durable data surface. Custom `toJSON` behavior is not
* executed; boundaries that persist a value first materialize a new plain-data
* record with {@link snapshotJsonValue}. Getters are invoked during this check,
* so callers that need a stable detached value use that one-pass materializer
* instead of checking and then rereading a side-effecting record.
* Test the same lossless JSON boundary as {@link snapshotJsonValue} without
* detaching it. Only own enumerable string properties participate; `toJSON`
* is ignored and getters run, so persistence boundaries use the snapshotter.
* @param value - the candidate event data to test.
* @param seen - objects on the current descent path, for circular-reference
* detection; the recursion threads it — callers omit it.
* @returns true when `value` survives a JSON round-trip losslessly.
* @param seen - current recursion path; callers omit it.
* @returns whether `value` survives JSON round-trip losslessly.
*/
export function isJsonValue(value: unknown, seen: Set<object> = new Set()): boolean {
if (value === null) return true

View File

@@ -7,10 +7,8 @@ import type { CallId } from '@deepseek-ai/dsh-llm'
import type { SessionEvent } from './types.ts'
/**
* Scan `events` for an open turn/step at the tail and return the synthetic boundary events
* that close them, with `seq` continuing the log and `time` copied from the last real event
* (the closers stand in for the crash moment; reusing the last timestamp keeps them
* deterministic and never invents a "future" time).
* Return deterministic synthetic events that close an open tail turn or step.
* Sequences continue the log and timestamps reuse the last real event.
*
* @param events - the loaded durable log to scan (a valid committed prefix, possibly with a crash tail).
* @returns the synthetic closer events to append after `events`, in order; empty when the log is already balanced.

View File

@@ -23,12 +23,8 @@ const SURFACE_EVENT_TYPES = new Set<string>([
])
/**
* Whether an event's `type` is surface-eligible (one of the five
* message-producing {@link SurfaceEventType} values). This is the TYPE check
* only — it does NOT require `surfaceOp` to be present. Use it to detect a
* surface-eligible event that is MISSING its mandatory marker (e.g. validating
* a seed/load log); use {@link isSurfaceEvent} to narrow to a fully-formed
* {@link SurfaceEvent} with `surfaceOp` present.
* Check only whether a type may enter the message surface. Use
* {@link isSurfaceEvent} when the mandatory `surfaceOp` must also be present.
* @param type - the event type string to test.
* @returns true when the type is one of the five message-producing types.
*/

View File

@@ -21,16 +21,7 @@ export function SessionId(id: string): SessionId {
export const SESSION_FORMAT_VERSION = 0
/**
* Immutable session metadata — written once at creation and never rewritten.
* {@link Session} enforces that contract at runtime: it validates and detaches
* the accepted scalar fields, requires this header's id to match the session
* id, and deep-freezes the published record.
*
* Kept SEPARATE from the event log deliberately: format-version, cwd, and
* lineage are storage concerns, not conversation events, so they stay out of
* {@link SessionEventMap} and never reach `deriveMessages()`. Every reference
* system (pi's `version: 3` header, Codex's `SessionMeta`, Claude Code's tail
* metadata) writes such a header.
* Immutable validated storage metadata, kept outside the conversation event log.
*/
export interface SessionHeader {
/**
@@ -63,17 +54,8 @@ export interface CreateSessionOptions {
/** Events to seed the new session with (replay/fork). */
readonly seed?: readonly SessionEvent[]
/**
* Creation metadata. The store reads this plain record and each accepted
* field once, then fills in `version`/`id` and defaults
* `createdAt` to now; the caller supplies the storage-level fields (validated
* absolute `cwd`, `parentSession` lineage, the seed boundary `seedLength`, and
* — when reconstructing a persisted session — the original `createdAt` to
* preserve it).
*
* `seedLength` is EXPLICIT, not inferred from `seed.length`: a reconstruction
* (resume/load) seeds the WHOLE stored log, so its `seed.length` is the full
* length, not the original boundary — the caller must pass the persisted
* boundary back. A fresh fork passes its actual seeded-prefix length.
* Storage metadata read once before publication. `seedLength` is explicit
* because a resumed seed contains the full stored log, not only its inherited prefix.
*/
readonly meta?: {
readonly cwd?: string
@@ -119,13 +101,8 @@ export interface TurnEndReasonMap {
disposed: { kind: 'disposed' }
'max-tokens': { kind: 'max-tokens' }
/**
* The turn's entire prompt batch was BLOCKED before any step ran — every
* drained queued message was vetoed by an `agent/prompt-submit` listener (a
* hook). The turn still opened (so the boundary stays balanced and the block
* is a durable in-turn fact), but ran zero steps. `reason` carries the block
* message from the vetoing decision. Distinct from `aborted` (a user-driven
* cancel) and `error` (a failure): the prompt was rejected by policy, not
* interrupted or broken. A UI renders it as "prompt blocked by hook".
* Policy blocked every prompt before the first step. The zero-step turn still
* records a balanced durable boundary and the veto reason.
*/
rejected: { kind: 'rejected'; reason: string }
/**
@@ -157,15 +134,9 @@ export interface TodoItem {
}
/**
* The request header: everything about an LLM request besides its derived
* message history — the call configuration plus the rendered system prompt,
* tool schemas, and the session prefix. Logged session state (the
* reconstructability RFC): a
* {@link SessionEventMap} `request/header` snapshot installs one, a
* `request/header-delta` amends it, and folding those events over the log
* (`foldRequestHeader`) reconstructs the header any request was built under.
* Canonical form: an empty system prompt, an empty tool list, and an empty
* prefix are ABSENT fields, matching how requests are built.
* Logged request state outside derived history: call config, system prompt,
* tools, and session prefix. Header snapshots and deltas reconstruct it;
* canonical empty optional fields are absent.
*/
export interface EpochHeader {
/** The conversation's call configuration (model + sampling scalars). */
@@ -356,16 +327,8 @@ export type SurfaceOp =
| { op: 'replace'; start: number; end: number }
/**
* Surface metadata passed to {@link Session.append}.
* `surfaceOp` controls how the event enters the surface linked list;
* `sourceEventSeqs` records the seq numbers of events that are provenance
* sources of this one (e.g. the `assistant/chunk` seqs behind an
* `assistant/message`, or the shadowed nodes behind a compaction replacement).
*
* Required for {@link SurfaceEventType} events — every message-producing event
* MUST declare how it enters the surface, because the surface is the sole
* source of derived history. Non-surface event types (`turn/start`,
* `assistant/chunk`, `error`, …) cannot carry surface metadata.
* Surface placement and provenance for {@link Session.append}. Required on
* message-producing events and forbidden on log-only events.
*/
export interface SurfaceIntent {
surfaceOp: SurfaceOp